{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,18]],"date-time":"2026-06-18T15:45:20Z","timestamp":1781797520387,"version":"3.54.5"},"publisher-location":"New York, NY, USA","reference-count":84,"publisher":"ACM","funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62401365, 62225112, 62132006, U24A20220"],"award-info":[{"award-number":["62401365, 62225112, 62132006, U24A20220"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100002858","name":"China Postdoctoral Science Foundation","doi-asserted-by":"publisher","award":["BX20250411, 2025M773473"],"award-info":[{"award-number":["BX20250411, 2025M773473"]}],"id":[{"id":"10.13039\/501100002858","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2025,10,27]]},"DOI":"10.1145\/3746027.3755332","type":"proceedings-article","created":{"date-parts":[[2025,10,25]],"date-time":"2025-10-25T06:54:15Z","timestamp":1761375255000},"page":"6928-6937","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":7,"title":["FVQ: A Large-Scale Dataset and an LMM-based Method for Face Video Quality Assessment"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0009-0000-7753-1596","authenticated-orcid":false,"given":"Sijing","family":"Wu","sequence":"first","affiliation":[{"name":"Shanghai Jiao Tong University, Shanghai, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7337-1748","authenticated-orcid":false,"given":"Yunhao","family":"Li","sequence":"additional","affiliation":[{"name":"Shanghai Jiao Tong University, Shanghai, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0002-4573-2224","authenticated-orcid":false,"given":"Ziwen","family":"Xu","sequence":"additional","affiliation":[{"name":"Shanghai Jiao Tong University, Shanghai, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6292-0529","authenticated-orcid":false,"given":"Yixuan","family":"Gao","sequence":"additional","affiliation":[{"name":"Shanghai Jiao Tong University, Shanghai, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6519-4067","authenticated-orcid":false,"given":"Huiyu","family":"Duan","sequence":"additional","affiliation":[{"name":"Shanghai Jiao Tong University, Shanghai, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8162-1949","authenticated-orcid":false,"given":"Wei","family":"Sun","sequence":"additional","affiliation":[{"name":"East China Normal University, Shanghai, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8165-9322","authenticated-orcid":false,"given":"Guangtao","family":"Zhai","sequence":"additional","affiliation":[{"name":"Shanghai Jiao Tong University, Shanghai, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2025,10,27]]},"reference":[{"key":"e_1_3_2_1_1_1","first-page":"3103","volume-title":"Proceedings of the 21st International Conference on Pattern Recognition (ICPR2012)","author":"Abaza Ayman","year":"2012","unstructured":"Ayman Abaza, Mary Ann Harrison, and Thirimachos Bourlai. 2012. Quality metrics for practical face recognition. In Proceedings of the 21st International Conference on Pattern Recognition (ICPR2012). IEEE, 3103-3107."},{"key":"e_1_3_2_1_2_1","doi-asserted-by":"publisher","DOI":"10.1109\/MCI.2007.353416"},{"key":"e_1_3_2_1_3_1","unstructured":"Shuai Bai Keqin Chen Xuejing Liu Jialin Wang Wenbin Ge Sibo Song Kai Dang Peng Wang Shijie Wang Jun Tang et al. 2025. Qwen2. 5-vl technical report. arXiv preprint arXiv:2502.13923 (2025)."},{"key":"e_1_3_2_1_4_1","doi-asserted-by":"publisher","DOI":"10.1109\/TIFS.2018.2799585"},{"key":"e_1_3_2_1_5_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.knosys.2022.108246"},{"key":"e_1_3_2_1_6_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00565"},{"key":"e_1_3_2_1_7_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.116"},{"key":"e_1_3_2_1_8_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00961"},{"key":"e_1_3_2_1_9_1","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2021.3088505"},{"key":"e_1_3_2_1_10_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00283"},{"key":"e_1_3_2_1_11_1","unstructured":"Zhe Chen Weiyun Wang Yue Cao Yangzhou Liu Zhangwei Gao Erfei Cui Jinguo Zhu Shenglong Ye Hao Tian Zhaoyang Liu et al. 2024b. Expanding Performance Boundaries of Open-Source Multimodal Models with Model Data and Test-Time Scaling. arXiv preprint arXiv:2412.05271 (2024)."},{"key":"e_1_3_2_1_12_1","unstructured":"Zesen Cheng Sicong Leng Hang Zhang Yifei Xin Xin Li Guanzheng Chen Yongxin Zhu Wenqi Zhang Ziyang Luo Deli Zhao et al. 2024. Videollama 2: Advancing spatial-temporal modeling and audio understanding in video-llms. arXiv preprint arXiv:2406.07476 (2024)."},{"key":"e_1_3_2_1_13_1","doi-asserted-by":"crossref","unstructured":"Huiyu Duan Qiang Hu Jiarui Wang Liu Yang Zitong Xu Lu Liu Xiongkuo Min Chunlei Cai Tianxiao Ye Xiaoyun Zhang et al. 2024. FineVQ: Fine-Grained User Generated Content Video Quality Assessment. arXiv preprint arXiv:2412.19238 (2024).","DOI":"10.1109\/CVPR52734.2025.00305"},{"key":"e_1_3_2_1_14_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00630"},{"key":"e_1_3_2_1_15_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-540-74549-5_26"},{"key":"e_1_3_2_1_16_1","volume-title":"LMM-VQA: Advancing video quality assessment with large multimodal models","author":"Ge Qihang","year":"2025","unstructured":"Qihang Ge, Wei Sun, Yu Zhang, Yunhao Li, Zhongpeng Ji, Fengyu Sun, Shangling Jui, Xiongkuo Min, and Guangtao Zhai. 2025. LMM-VQA: Advancing video quality assessment with large multimodal models. IEEE Transactions on Circuits and Systems for Video Technology (2025)."},{"key":"e_1_3_2_1_17_1","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2017.2707479"},{"key":"e_1_3_2_1_18_1","volume-title":"The distributed human neural system for face perception. Trends in cognitive sciences","author":"Haxby James V","year":"2000","unstructured":"James V Haxby, Elizabeth A Hoffman, and M Ida Gobbini. 2000. The distributed human neural system for face perception. Trends in cognitive sciences, Vol. 4, 6 (2000), 223-233."},{"key":"e_1_3_2_1_19_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICB45273.2019.8987255"},{"key":"e_1_3_2_1_20_1","doi-asserted-by":"publisher","DOI":"10.1109\/QoMEX.2017.7965673"},{"key":"e_1_3_2_1_21_1","first-page":"3","article-title":"Lora: Low-rank adaptation of large language models","volume":"1","author":"Hu Edward J","year":"2022","unstructured":"Edward J Hu, Yelong Shen, Phillip Wallis, Zeyuan Allen-Zhu, Yuanzhi Li, Shean Wang, Lu Wang, Weizhu Chen, et al., 2022. Lora: Low-rank adaptation of large language models. ICLR, Vol. 1, 2 (2022), 3.","journal-title":"ICLR"},{"key":"e_1_3_2_1_22_1","unstructured":"TikTok Inc. 2016. TikTok. https:\/\/www.tiktok.com"},{"key":"e_1_3_2_1_23_1","volume-title":"Kyu Park, and Sungeun Hong. 2023. Ifqa: Interpretable face quality assessment. In Proceedings of the IEEE\/CVF winter conference on applications of computer vision. 3444-3453","author":"Jo Byungho","unstructured":"Byungho Jo, Donghyeon Cho, In Kyu Park, and Sungeun Hong. 2023. Ifqa: Interpretable face quality assessment. In Proceedings of the IEEE\/CVF winter conference on applications of computer vision. 3444-3453."},{"key":"e_1_3_2_1_24_1","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2021.3130541"},{"key":"e_1_3_2_1_25_1","doi-asserted-by":"publisher","DOI":"10.1523\/JNEUROSCI.17-11-04302.1997"},{"key":"e_1_3_2_1_26_1","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2019.2923051"},{"key":"e_1_3_2_1_27_1","doi-asserted-by":"publisher","DOI":"10.1007\/s00521-021-06535-0"},{"key":"e_1_3_2_1_28_1","doi-asserted-by":"publisher","DOI":"10.1145\/3343031.3351028"},{"key":"e_1_3_2_1_29_1","volume-title":"Perceptual quality assessment of face video compression: A benchmark and an effective method","author":"Li Yixuan","year":"2024","unstructured":"Yixuan Li, Bolin Chen, Baoliang Chen, Meng Wang, Shiqi Wang, and Weisi Lin. 2024. Perceptual quality assessment of face video compression: A benchmark and an effective method. IEEE Transactions on Multimedia (2024)."},{"key":"e_1_3_2_1_30_1","doi-asserted-by":"publisher","DOI":"10.1109\/MIPR49039.2020.00015"},{"key":"e_1_3_2_1_31_1","doi-asserted-by":"publisher","DOI":"10.1145\/3503161.3547849"},{"key":"e_1_3_2_1_32_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCT46805.2019.8947255"},{"key":"e_1_3_2_1_33_1","volume-title":"Video-llava: Learning united visual representation by alignment before projection. arXiv preprint arXiv:2311.10122","author":"Lin Bin","year":"2023","unstructured":"Bin Lin, Yang Ye, Bin Zhu, Jiaxi Cui, Munan Ning, Peng Jin, and Li Yuan. 2023. Video-llava: Learning united visual representation by alignment before projection. arXiv preprint arXiv:2311.10122 (2023)."},{"key":"e_1_3_2_1_34_1","doi-asserted-by":"publisher","DOI":"10.1109\/WACV51458.2022.00319"},{"key":"e_1_3_2_1_35_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02484"},{"key":"e_1_3_2_1_36_1","volume-title":"Visual instruction tuning. Advances in neural information processing systems","author":"Liu Haotian","year":"2023","unstructured":"Haotian Liu, Chunyuan Li, Qingyang Wu, and Yong Jae Lee. 2023. Visual instruction tuning. Advances in neural information processing systems, Vol. 36 (2023), 34892-34916."},{"key":"e_1_3_2_1_37_1","doi-asserted-by":"publisher","DOI":"10.1109\/TCDS.2025.3529177"},{"key":"e_1_3_2_1_38_1","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2024.3350049"},{"key":"e_1_3_2_1_39_1","unstructured":"Haoyu Lu Wen Liu Bo Zhang Bingxuan Wang Kai Dong Bo Liu Jingxiang Sun Tongzheng Ren Zhuoshu Li Hao Yang et al. 2024b. Deepseek-vl: towards real-world vision-language understanding. arXiv preprint arXiv:2403.05525 (2024)."},{"key":"e_1_3_2_1_40_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02453"},{"key":"e_1_3_2_1_41_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01400"},{"key":"e_1_3_2_1_42_1","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2015.2502725"},{"key":"e_1_3_2_1_43_1","doi-asserted-by":"publisher","DOI":"10.5555\/3104322.3104425"},{"key":"e_1_3_2_1_44_1","volume-title":"Facexformer: A unified transformer for facial analysis. arXiv preprint arXiv:2403.12960","author":"Narayan Kartik","year":"2024","unstructured":"Kartik Narayan, Vibashan VS, Rama Chellappa, and Vishal M Patel. 2024. Facexformer: A unified transformer for facial analysis. arXiv preprint arXiv:2403.12960 (2024)."},{"key":"e_1_3_2_1_45_1","first-page":"3073","volume-title":"CVD2014-A database for evaluating no-reference video quality assessment algorithms. IEEE Transactions on Image Processing","volume":"25","author":"Nuutinen Mikko","year":"2016","unstructured":"Mikko Nuutinen, Toni Virtanen, Mikko Vaahteranoksa, Tero Vuori, Pirkko Oittinen, and Jukka H\u00e4kkinen. 2016. CVD2014-A database for evaluating no-reference video quality assessment algorithms. IEEE Transactions on Image Processing, Vol. 25, 7 (2016), 3073-3086."},{"key":"e_1_3_2_1_46_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00758"},{"key":"e_1_3_2_1_47_1","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2024.3358697"},{"key":"e_1_3_2_1_48_1","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2014.2299154"},{"key":"e_1_3_2_1_49_1","doi-asserted-by":"publisher","DOI":"10.1145\/3507901"},{"key":"e_1_3_2_1_50_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298682"},{"key":"e_1_3_2_1_51_1","doi-asserted-by":"publisher","DOI":"10.17671\/gazibtd.1399077"},{"key":"e_1_3_2_1_52_1","volume-title":"Recommendation ITU-R BT","volume":"500","author":"Series B","year":"2012","unstructured":"B Series. 2012. Methodology for the subjective assessment of the quality of television pictures. Recommendation ITU-R BT, Vol. 500, 13 (2012)."},{"key":"e_1_3_2_1_53_1","volume-title":"Alan Conrad Bovik, and Lawrence K Cormack","author":"Seshadrinathan Kalpana","year":"2010","unstructured":"Kalpana Seshadrinathan, Rajiv Soundararajan, Alan Conrad Bovik, and Lawrence K Cormack. 2010. Study of subjective and objective quality assessment of video. IEEE transactions on Image Processing, Vol. 19, 6 (2010), 1427-1441."},{"key":"e_1_3_2_1_54_1","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2018.2869673"},{"key":"e_1_3_2_1_55_1","volume-title":"A tutorial on support vector regression. Statistics and computing","author":"Smola Alex J","year":"2004","unstructured":"Alex J Smola and Bernhard Sch\u00f6lkopf. 2004. A tutorial on support vector regression. Statistics and computing, Vol. 14 (2004), 199-222."},{"key":"e_1_3_2_1_56_1","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2023.3301276"},{"key":"e_1_3_2_1_57_1","doi-asserted-by":"publisher","DOI":"10.1145\/3503161.3548329"},{"key":"e_1_3_2_1_58_1","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2024.3385364"},{"key":"e_1_3_2_1_59_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00569"},{"key":"e_1_3_2_1_60_1","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2021.3072221"},{"key":"e_1_3_2_1_61_1","doi-asserted-by":"publisher","DOI":"10.1109\/OJSP.2021.3090333"},{"key":"e_1_3_2_1_62_1","unstructured":"Peng Wang Shuai Bai Sinan Tan Shijie Wang Zhihao Fan Jinze Bai Keqin Chen Xuejing Liu Jialin Wang Wenbin Ge et al. 2024a. Qwen2-vl: Enhancing vision-language model's perception of the world at any resolution. arXiv preprint arXiv:2409.12191 (2024)."},{"key":"e_1_3_2_1_63_1","volume-title":"A survey of deep face restoration: Denoise, super-resolution, deblur, artifact removal. arXiv preprint arXiv:2211.02831","author":"Wang Tao","year":"2022","unstructured":"Tao Wang, Kaihao Zhang, Xuanxi Chen, Wenhan Luo, Jiankang Deng, Tong Lu, Xiaochun Cao, Wei Liu, Hongdong Li, and Stefanos Zafeiriou. 2022. A survey of deep face restoration: Denoise, super-resolution, deblur, artifact removal. arXiv preprint arXiv:2211.02831 (2022)."},{"key":"e_1_3_2_1_64_1","unstructured":"Weiyun Wang Zhe Chen Wenhai Wang Yue Cao Yangzhou Liu Zhangwei Gao Jinguo Zhu Xizhou Zhu Lewei Lu Yu Qiao et al. 2024b. Enhancing the reasoning ability of multimodal large language models via mixed preference optimization. arXiv preprint arXiv:2411.10442 (2024)."},{"key":"e_1_3_2_1_65_1","doi-asserted-by":"publisher","DOI":"10.1109\/MMSP.2019.8901772"},{"key":"e_1_3_2_1_66_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01323"},{"key":"e_1_3_2_1_67_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20068-7_31"},{"key":"e_1_3_2_1_68_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01843"},{"key":"e_1_3_2_1_69_1","doi-asserted-by":"publisher","DOI":"10.1145\/3581783.3611737"},{"key":"e_1_3_2_1_70_1","volume-title":"Q-align: Teaching lmms for visual scoring via discrete text-defined levels. arXiv preprint arXiv:2312.17090","author":"Wu Haoning","year":"2023","unstructured":"Haoning Wu, Zicheng Zhang, Weixia Zhang, Chaofeng Chen, Liang Liao, Chunyi Li, Yixuan Gao, Annan Wang, Erli Zhang, Wenxiu Sun, et al., 2023c. Q-align: Teaching lmms for visual scoring via discrete text-defined levels. arXiv preprint arXiv:2312.17090 (2023)."},{"key":"e_1_3_2_1_71_1","volume-title":"Clipvqa: Video quality assessment via clip","author":"Xing Fengchuang","year":"2024","unstructured":"Fengchuang Xing, Mingjie Li, Yuan-Gen Wang, Guopu Zhu, and Xiaochun Cao. 2024. Clipvqa: Video quality assessment via clip. IEEE Transactions on Broadcasting (2024)."},{"key":"e_1_3_2_1_72_1","volume-title":"Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition. 14019-14029","author":"Ying Zhenqiang","year":"2021","unstructured":"Zhenqiang Ying, Maniratnam Mandal, Deepti Ghadiyaram, and Alan Bovik. 2021. Patch-vq:'patching up'the video quality problem. In Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition. 14019-14029."},{"key":"e_1_3_2_1_73_1","doi-asserted-by":"publisher","DOI":"10.1145\/3474085.3475368"},{"key":"e_1_3_2_1_74_1","unstructured":"YouTube. 2005. YouTube. https:\/\/www.youtube.com"},{"key":"e_1_3_2_1_75_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01422"},{"key":"e_1_3_2_1_76_1","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2021.3107213"},{"key":"e_1_3_2_1_77_1","doi-asserted-by":"publisher","DOI":"10.1145\/3581783.3612023"},{"key":"e_1_3_2_1_78_1","doi-asserted-by":"publisher","DOI":"10.1109\/TCYB.2023.3338615"},{"key":"e_1_3_2_1_79_1","unstructured":"Boqiang Zhang Kehan Li Zesen Cheng Zhiqiang Hu Yuqian Yuan Guanzheng Chen Sicong Leng Yuming Jiang Hang Zhang Xin Li et al. 2025. VideoLLaMA 3: frontier multimodal foundation models for image and video understanding. arXiv preprint arXiv:2501.13106 (2025)."},{"key":"e_1_3_2_1_80_1","doi-asserted-by":"publisher","DOI":"10.1109\/LSP.2016.2603342"},{"key":"e_1_3_2_1_81_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00174"},{"key":"e_1_3_2_1_82_1","doi-asserted-by":"publisher","DOI":"10.1145\/3373509.3373558"},{"key":"e_1_3_2_1_83_1","doi-asserted-by":"publisher","DOI":"10.1109\/LSP.2022.3215311"},{"key":"e_1_3_2_1_84_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20071-7_38"}],"event":{"name":"MM '25: The 33rd ACM International Conference on Multimedia","location":"Dublin Ireland","acronym":"MM '25","sponsor":["SIGMM ACM Special Interest Group on Multimedia"]},"container-title":["Proceedings of the 33rd ACM International Conference on Multimedia"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3746027.3755332","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,12,10]],"date-time":"2025-12-10T04:05:29Z","timestamp":1765339529000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3746027.3755332"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,27]]},"references-count":84,"alternative-id":["10.1145\/3746027.3755332","10.1145\/3746027"],"URL":"https:\/\/doi.org\/10.1145\/3746027.3755332","relation":{},"subject":[],"published":{"date-parts":[[2025,10,27]]},"assertion":[{"value":"2025-10-27","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}